Vision Model Leaderboard: Best Vision-Language Models
Ranked by LMArena Vision Arena scores: users upload an image, ask a question, and vote between two anonymous models’ answers.
- Top open-weight
GLM-5.3-Flash1318Z.ai
In LMArena Vision Arena data published Oct 19, 2026, Anthropic’s Claude Fable 5 (High) ranks #1 of 167 models with 1325 (14,714 votes).
Full leaderboard · Homework
30 modelsSorted by LMArena score by default; ± is half the 95% confidence interval. Category columns show the model’s score on that sub-board; – means no score.
| # | Model | LMArena · Homework | License | ||
|---|---|---|---|---|---|
| Score↓ | Rank | Votes | |||
| 1 | GLM-5.3-FlashZ.aiOpen |
1318±13 | 22 | 2,229 | MIT |
| 2 |  Kimi K2.6Moonshot AIOpen |
1310±13 | 30 | 2,263 | Modified MIT |
| 3 |  Gemma 4 31BGoogleOpen |
1310±9 | 31 | 6,435 | Apache 2.0 |
| 4 |  DeepSeek-V4.1-Flash-20260910 (Max)DeepSeekOpen |
1307±25 | 34 | 521 | MIT |
| 5 | Kimi K2.5 (Thinking)Moonshot AIOpen |
1297±10 | 38 | 3,649 | Modified MIT |
| 6 |  Qwen3.8-27BAlibabaOpen |
1295±20 | 43 | 919 | Apache 2.0 |
| 7 | Gemma 4 26B A4BGoogleOpen |
1293±10 | 44 | 3,822 | Apache 2.0 |
| 8 | Qwen3.5-397B-A17BAlibabaOpen |
1292±10 | 45 | 4,001 | Apache 2.0 |
| 9 |  MiMo-V2.6-FlashXiaomiOpen |
1283±26 | 54 | 546 | MIT |
| 10 | Qwen3-VL-235B-A22B-InstructAlibabaOpen |
1277±14 | 58 | 1,611 | Apache 2.0 |
| 11 |  MiniMax-M3MiniMaxOpen |
1268±13 | 65 | 2,405 | MiniMax Community License |
| 12 | MiMo-V2.6-ProXiaomiOpen |
1264±39 | 67 | 226 | MIT |
| 13 | Kimi K2.5 (Instant)Moonshot AIOpen |
1264±23 | 68 | 573 | Modified MIT |
| 14 | MiMo-V2.5XiaomiOpen |
1262±10 | 69 | 4,076 | MIT |
| 15 | Qwen3.5-122B-A10BAlibabaOpen |
1261±14 | 70 | 1,929 | Apache 2.0 |
| 16 | TInkling-SmallThinking MachinesOpen | 1257±20 | 73 | 835 | Apache 2.0 |
| 17 | Qwen3.5-27BAlibabaOpen |
1256±10 | 74 | 3,843 | Apache 2.0 |
| 18 | Qwen3-VL-235B-A22B-ThinkingAlibabaOpen |
1234±32 | 84 | 298 | Apache 2.0 |
| 19 |  Mistral Medium 3.5Mistral AIOpen |
1230±22 | 87 | 803 | Modified MIT |
| 20 | NNVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)NVIDIAOpen | 1229±32 | 88 | 380 | OpenMDW-1.1 |
| 21 | Mistral Large 3Mistral AIOpen |
1216±20 | 92 | 977 | Apache 2.0 |
| 22 | SStep-3StepFunOpen | 1183±39 | 101 | 215 | Apache 2.0 |
| 23 | Mistral Small 3.2 (2506)Mistral AIOpen |
1173±24 | 103 | 614 | Apache 2.0 |
| 24 |  Llama 4 Maverick 17B 128E InstructMetaOpen |
1164±25 | 108 | 526 | Llama 4 |
| 25 | GLM-4.5VZ.aiOpen |
1163±38 | 109 | 215 | MIT |
| 26 | Gemma 3 27B ITGoogleOpen |
1160±19 | 110 | 1,034 | Gemma |
| 27 | Mistral Small 3.1 24B Instruct (2503)Mistral AIOpen |
1158±21 | 111 | 809 | Apache 2.0 |
| 28 | GLM-4.6VZ.aiOpen |
1155±36 | 113 | 271 | MIT |
| 29 | Llama 4 Scout 17B 16E InstructMetaOpen |
1148±26 | 115 | 477 | Llama |
| 30 |  Molmo 2 8BAi2Open |
1069±50 | 118 | 187 | Apache 2.0 |
Scores: LMArena leaderboard-dataset (lmarena-ai on Hugging Face, CC-BY-4.0, vision config), Homework published Oct 19, 2026. Please credit the source when citing.
Sources & methodology
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
Vision config, published Oct 19, 2026; 167 models on the overall board.
- Scores are Bradley-Terry Arena ratings fitted from human votes between two anonymous answers to the same image prompt.
- Categories (OCR, diagrams, homework, captioning, Chinese/English…) are separate LMArena boards computed on prompts of that type, not a breakdown of the overall score; ranks can differ a lot.
- Fields without public data (price, context length, release date…) are not shown; blanks are –. Nothing is estimated.
- Synced daily. JSON API: /api/public/vision-leaderboard.php
This week
Collecting data: 1/7 days recorded; weekly changes appear after 7 days
Synced automatically once a day; ranks are compared only between real snapshots, never backfilled.FAQ
What is the best vision-language model right now?
In LMArena Vision Arena data published Oct 19, 2026, Anthropic’s Claude Fable 5 (High) ranks #1 of 167 models with 1325 (14,714 votes).
What is each vendor’s best vision model?
Top overall entry per vendor: Anthropic Claude Fable 5 (High) (1325, #1), Google Gemini 3.8 Flash (High) (1315, #7), Alibaba Qwen3.8-Max (1313, #10), Meta Muse Spark 1.3 (Max) (1308, #12), OpenAI GPT-5.4 (High) (1303, #18).
Which model is best at OCR?
On LMArena’s OCR board (123 models), Claude Fable 5 (High) is #1 with 1337.
What is the best open-weight vision model?
50 open-weight models are listed; the top one is GLM-5.3-Flash (1294, MIT).
How is this different from benchmarks like MMMU?
MMMU and similar benchmarks auto-score a fixed question set; this board comes from blind human votes on people’s own images and questions, reflecting real-use preference. They are not convertible.